A recent development in deep learning techniques has attracted attention to the decoding and classification of electroencephalogram (EEG) signals. Despite several efforts to utilize different features in EEG signals, a significant research challenge is using time-dependent features in combination with local and global features. Several attempts have been made to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information. These features are usually either handcrafted features, such as power ratios, or splitting data into smaller-sized windows related to specific properties, such as a peak at 300 ms. However, these approaches partially solve the problem but simultaneously hinder CNNs' capability to learn from unknown information that might be present in the data. Other approaches, like recurrent neural networks, are very suitable for learning time-dependent information from EEG signals in the presence of unrelated sequential data. To solve this, we have proposed an encoding kernel (EnK), a novel time-encoding approach, which uniquely introduces time decomposition information during the vertical convolution operation in CNNs. The encoded information lets CNNs learn time-dependent features in addition to local and global features. We performed extensive experiments on several EEG data sets—physical human-robot collaborations, P300 visual-evoked potentials, motor imagery, movement-related cortical potentials, and the Dataset for Emotion Analysis Using Physiological Signals. The EnK outperforms the state of the art with an up to 6.5% reduction in mean squared error (MSE) and a 9.5% improvement in F1-scores compared to the average for all data sets together compared to base models. These results support our approach and show a high potential to improve the performance of physiological and non-physiological data. Moreover, the EnK can be applied to virtually any deep learning architecture with minimal effort.

Singh, A.k., Bianchi, L. (2024). Encoding temporal information in deep convolution neural network. FRONTIERS IN NEUROERGONOMICS, 5 [10.3389/fnrgo.2024.1287794].

Encoding temporal information in deep convolution neural network

Bianchi, Luigi
Membro del Collaboration Group
2024-06-19

Abstract

A recent development in deep learning techniques has attracted attention to the decoding and classification of electroencephalogram (EEG) signals. Despite several efforts to utilize different features in EEG signals, a significant research challenge is using time-dependent features in combination with local and global features. Several attempts have been made to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information. These features are usually either handcrafted features, such as power ratios, or splitting data into smaller-sized windows related to specific properties, such as a peak at 300 ms. However, these approaches partially solve the problem but simultaneously hinder CNNs' capability to learn from unknown information that might be present in the data. Other approaches, like recurrent neural networks, are very suitable for learning time-dependent information from EEG signals in the presence of unrelated sequential data. To solve this, we have proposed an encoding kernel (EnK), a novel time-encoding approach, which uniquely introduces time decomposition information during the vertical convolution operation in CNNs. The encoded information lets CNNs learn time-dependent features in addition to local and global features. We performed extensive experiments on several EEG data sets—physical human-robot collaborations, P300 visual-evoked potentials, motor imagery, movement-related cortical potentials, and the Dataset for Emotion Analysis Using Physiological Signals. The EnK outperforms the state of the art with an up to 6.5% reduction in mean squared error (MSE) and a 9.5% improvement in F1-scores compared to the average for all data sets together compared to base models. These results support our approach and show a high potential to improve the performance of physiological and non-physiological data. Moreover, the EnK can be applied to virtually any deep learning architecture with minimal effort.
19-giu-2024
Pubblicato
Rilevanza internazionale
Articolo
Sì, ma tipo non specificato
Settore INF/01
Settore ING-INF/06
Settore INFO-01/A - Informatica
Settore IBIO-01/A - Bioingegneria
English
Singh, A.k., Bianchi, L. (2024). Encoding temporal information in deep convolution neural network. FRONTIERS IN NEUROERGONOMICS, 5 [10.3389/fnrgo.2024.1287794].
Singh, Ak; Bianchi, L
Articolo su rivista
File in questo prodotto:
File Dimensione Formato  
fnrgo-05-1287794.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 1.75 MB
Formato Adobe PDF
1.75 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/372623
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact